| --- |
| library_name: transformers |
| license: mit |
| base_model: FacebookAI/xlm-roberta-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - f1 |
| model-index: |
| - name: Revision_Meta_XLM |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # Revision_Meta_XLM |
|
|
| This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.4710 |
| - Accuracy: 0.9220 |
| - F1: 0.7251 |
|
|
| ## Model description |
|
|
| More information needed |
|
|
| ## Intended uses & limitations |
|
|
| More information needed |
|
|
| ## Training and evaluation data |
|
|
| More information needed |
|
|
| ## Training procedure |
|
|
| ### Training hyperparameters |
|
|
| The following hyperparameters were used during training: |
| - learning_rate: 2e-05 |
| - train_batch_size: 32 |
| - eval_batch_size: 32 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - num_epochs: 15 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
| |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:| |
| | No log | 0.5102 | 150 | 0.3977 | 0.8526 | 0.4695 | |
| | 0.5230 | 1.0204 | 300 | 0.2417 | 0.9188 | 0.7149 | |
| | 0.5230 | 1.5306 | 450 | 0.2309 | 0.9220 | 0.7111 | |
| | 0.2723 | 2.0408 | 600 | 0.2386 | 0.9180 | 0.7130 | |
| | 0.2723 | 2.5510 | 750 | 0.2537 | 0.9259 | 0.7229 | |
| | 0.2107 | 3.0612 | 900 | 0.2225 | 0.9354 | 0.7547 | |
| | 0.2107 | 3.5714 | 1050 | 0.2462 | 0.9330 | 0.7376 | |
| | 0.1682 | 4.0816 | 1200 | 0.3432 | 0.9117 | 0.7101 | |
| | 0.1682 | 4.5918 | 1350 | 0.2572 | 0.9267 | 0.7195 | |
| | 0.1499 | 5.1020 | 1500 | 0.3172 | 0.9243 | 0.7344 | |
| | 0.1499 | 5.6122 | 1650 | 0.3080 | 0.9212 | 0.7206 | |
| | 0.1219 | 6.1224 | 1800 | 0.3767 | 0.9133 | 0.6921 | |
| | 0.1219 | 6.6327 | 1950 | 0.4346 | 0.9039 | 0.7024 | |
| | 0.1055 | 7.1429 | 2100 | 0.3059 | 0.9338 | 0.7309 | |
| | 0.1055 | 7.6531 | 2250 | 0.3716 | 0.9236 | 0.7237 | |
| | 0.0786 | 8.1633 | 2400 | 0.4106 | 0.9188 | 0.7174 | |
| | 0.0786 | 8.6735 | 2550 | 0.4007 | 0.9228 | 0.7250 | |
| | 0.0673 | 9.1837 | 2700 | 0.4195 | 0.9236 | 0.7309 | |
| | 0.0673 | 9.6939 | 2850 | 0.4486 | 0.9149 | 0.7102 | |
| | 0.0589 | 10.2041 | 3000 | 0.5117 | 0.9078 | 0.6939 | |
| | 0.0589 | 10.7143 | 3150 | 0.4755 | 0.9149 | 0.7154 | |
| | 0.0494 | 11.2245 | 3300 | 0.4287 | 0.9204 | 0.7198 | |
| | 0.0494 | 11.7347 | 3450 | 0.3905 | 0.9314 | 0.7322 | |
| | 0.0426 | 12.2449 | 3600 | 0.4332 | 0.9243 | 0.7333 | |
| | 0.0426 | 12.7551 | 3750 | 0.4228 | 0.9307 | 0.7385 | |
| | 0.0339 | 13.2653 | 3900 | 0.4589 | 0.9275 | 0.7380 | |
| | 0.0339 | 13.7755 | 4050 | 0.5148 | 0.9141 | 0.7128 | |
| | 0.0272 | 14.2857 | 4200 | 0.4624 | 0.9236 | 0.7273 | |
| | 0.0272 | 14.7959 | 4350 | 0.4710 | 0.9220 | 0.7251 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.3.0 |
| - Pytorch 2.9.0+cu126 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.2 |
| |
